memory_eval

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral burden, but it does not. It fails to disclose potential side effects (e.g., whether write_report creates files), whether the tool performs read-only operations, how long it might take, or what the output looks like. The parameter write_report hints at a side effect, but the description does not explain it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It efficiently communicates the primary action. However, it is so brief that it omits essential details, which is a trade-off. Still, as a concise statement, it earns a high score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 2 parameters, no annotations, no output schema, and no parameter descriptions. The description does not explain return values, side effects, or how to interpret the metrics. Given the tool's evaluative nature, an agent needs to know whether it writes files, what data it accesses, and how to use the reported metrics. The description falls short.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no parameter information. The 'top' parameter likely relates to k in recall@k, but this is not explicitly stated. 'write_report' is completely unexplained. The agent must guess at their meanings from parameter names and defaults alone, which is insufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action: run the SecondBrain retrieval regression suite and report specific metrics (recall@k and mean reciprocal rank). This distinguishes it from sibling tools like memory_search and memory_get, which are for individual queries or retrieval, not for evaluating overall retrieval performance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The use case is implied: the tool is for evaluating retrieval performance. However, there is no explicit guidance on when to use it versus alternatives, nor any mention of prerequisites or exclusions. For example, it does not say 'use this instead of memory_search for benchmarking' or 'do not use in production with live data.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.